Temporal Prediction Research Articles

A Semantic Web-Based Approach for Bat Trajectory Reconstruction With Human Keypoint Information

Restoring the trajectory of a bat from a table tennis match video is critical in analyzing a table tennis technique and conducting statistical analysis. However, directly bat location detection in each frame is challenging due to changing shapes caused by varying movement directions and speeds, leading to ambiguity. This paper develops a novel two-stage method. The first stage utilizes YOLO for bat detection in each frame, followed by filtering out erroneous candidate boxes. In the second stage, the authors use a temporal prediction model that integrating human keypoint information and interpolation to reconstruct a complete bat trajectory with minimal errors. The method's effectiveness and performance are evaluated on our video datasets. The evaluation results demonstrate that the proposed method outperforms traditional methods on precision performance metrics. The error screening algorithm improves precision score to nearly 1. In addition, the method has the recall score 22.3% higher than YOLO 's and also 1.4% higher than that of YOLO with cubic spline interpolation.

Unveiling the impact of auditory salience and sources identification on perceived pleasantness in environmental soundscapes

On the basis of initial results related to modulations of auditory salience— the ability to capture attention—by timbre attributes (especially, brightness and roughness), the present study investigates auditory salience as a predictor of perceived pleasantness in environmental sound scenes. A new paradigm was set up to measure continuous pleasantness while observing the impact of specific events, in a corpus of 11 various soundscapes. Specific events were found to affect perceived pleasantness, in a source-dependent direction in line with the literature. In addition, causality analyses examined the impact of temporal salience predictions on pleasantness ratings, along with other indices (equivalent sound level, loudness, or timbre attributes). They showed that salience was the best predictor of pleasantness, ahead of loudness, level or brightness and roughness. Nonetheless, the last two turned out to play, as well, a significant role in the pleasantness percept. Therefore, auditory salience is confirmed as a relevant indicator for assessing the perception of soundscapes, and the identification of sound sources that compose them is also confirmed to be crucial in this assessment.

Super Resolution Graph With Conditional Normalizing Flows for Temporal Link Prediction

Super Resolution Graph With Conditional Normalizing Flows for Temporal Link Prediction

Temporal prediction of dissolved oxygen based on CEEMDAN and multi-strategy LSTM hybrid model

Temporal prediction of dissolved oxygen based on CEEMDAN and multi-strategy LSTM hybrid model

Prediction of 4D stress field evolution around additive manufacturing-induced porosity through progressive deep-learning frameworks

This study investigates the application of machine learning models to predict time-evolving stress fields in complex three-dimensional structures trained with full-scale finite element simulation data. Two novel architectures, the multi-decoder CNN (MUDE-CNN) and the multiple encoder–decoder model with transfer learning (MTED-TL), were introduced to address the challenge of predicting the progressive and spatial evolutional of stress distributions around defects. The MUDE-CNN leveraged a shared encoder for simultaneous feature extraction and employed multiple decoders for distinct time frame predictions, while MTED-TL progressively transferred knowledge from one encoder–decoder block to another, thereby enhancing prediction accuracy through transfer learning. These models were evaluated to assess their accuracy, with a particular focus on predicting temporal stress fields around an additive manufacturing (AM)-induced isolated pore, as understanding such defects is crucial for assessing mechanical properties and structural integrity in materials and components fabricated via AM. The temporal model evaluation demonstrated MTED-TL’s consistent superiority over MUDE-CNN, owing to transfer learning’s advantageous initialization of weights and smooth loss curves. Furthermore, an autoregressive training framework was introduced to improve temporal predictions, consistently outperforming both MUDE-CNN and MTED-TL. By accurately predicting temporal stress fields around AM-induced defects, these models can enable real-time monitoring and proactive defect mitigation during the fabrication process. This capability ensures enhanced component quality and enhances the overall reliability of additively manufactured parts.

A finite element-inspired hypergraph neural network: Application to fluid dynamics simulations

An emerging trend in deep learning research focuses on the applications of graph neural networks (GNNs) for mesh-based continuum mechanics simulations. Most of these learning frameworks operate on graphs wherein each edge connects two nodes. Inspired by the data connectivity in the finite element method, we present a method to construct a hypergraph by connecting the nodes by elements rather than edges. A hypergraph message-passing network is defined on such a node-element hypergraph that mimics the calculation process of local stiffness matrices. We term this method a finite element-inspired hypergraph neural network, in short FEIH(ϕ)-GNN. We further equip the proposed network with rotation equivariance, and explore its capability for modeling unsteady fluid flow systems. The effectiveness of the network is demonstrated on two common benchmark problems, namely the fluid flow around a circular cylinder and airfoil configurations. Stabilized and accurate temporal roll-out predictions can be obtained using the ϕ-GNN framework within the interpolation Reynolds number range. The network is also able to extrapolate moderately towards higher Reynolds number domain out of the training range.

Sequential stacking link prediction algorithms for temporal networks

Link prediction algorithms are indispensable tools in many scientific applications by speeding up network data collection and imputing missing connections. However, in many systems, links change over time and it remains unclear how to optimally exploit such temporal information for link predictions in such networks. Here, we show that many temporal topological features, in addition to having high computational cost, are less accurate in temporal link prediction than sequentially stacked static network features. This sequential stacking link prediction method uses 41 static network features that avoid detailed feature engineering choices and is capable of learning a highly accurate predictive distribution of future connections from historical data. We demonstrate that this algorithm works well for both partially observed and completely unobserved target layers, and on two temporal stochastic block models achieves near-oracle-level performance when combined with other single predictor methods as an ensemble learning method. Finally, we empirically illustrate that stacking multiple predictive methods together further improves performance on 19 real-world temporal networks from different domains.

Efficient VVC Encoding Using Hierarchical Parallelization: A Comprehensive Analysis

This paper presents and analyzes different parallelization strategies in VVenC, an open and optimized software encoder implementation of the Versatile Video Coding (VVC) standard. VVC has been developed to address the increasing demand for higher compression of digital video data, and it reduces the bitrate by around 50% for the same perceived quality compared to its predecessor, the High-Efficiency Video Coding (HEVC) standard. However, this increase in compression efficiency comes with an increase in computational complexity, particularly on the encoder side. VVenC integrates algorithmic optimizations for each coding tool in VVC and defines a set of five presets from faster to slower that provide Pareto-optimal tradeoffs between runtime and efficiency. Multithreading is employed to further reduce runtime while preserving most of the compression efficiency of each preset. With a hierarchical combination of pre-processing, picture-level and in-picture parallelization, VVenC achieves a 4× speedup for four threads. Further speedup using a higher number of threads depends on the video resolution and used encoder preset. For 16 threads, it ranges from 6 to 9 for high definition to 10-12 for ultra-high-definition video. Compared to previous work, the usage of temporal prediction for the adaptive loop filter reduces the associated coding efficiency loss from 0.4% to almost zero. A better scaling for higher numbers of threads can be achieved at the cost of a higher coding efficiency loss. In the presented framework, increased speedup by smaller block Coding Tree Unit (CTU) sizes, a combination of wavefront parallel processing and various tiles picture partitioning configurations is examined. Furthermore, results on a 20-core ARM-based Apple M1 computer indicate a better scaling for multithreading compared to × 86-based architectures. The analysis is complemented by profiling, which exhibits the overhead by idle threads and identifies the mode estimation as the main bottleneck of the presented framework.

Evaluating the Bayesian causal inference model of intentional binding through computational modeling.

Intentional binding refers to the subjective compression of the time interval between an action and its consequence. While intentional binding has been widely used as a proxy for the sense of agency, its underlying mechanism has been largely veiled. Bayesian causal inference (BCI) has gained attention as a potential explanation, but currently lacks sufficient empirical support. Thus, this study implemented various computational models to describe the possible mechanisms of intentional binding, fitted them to individual observed data, and quantitatively evaluated their performance. The BCI models successfully isolated the parameters that potentially contributed to intentional binding (i.e., causal belief and temporal prediction) and generally better explained an observer's time estimation than traditional models such as maximum likelihood estimation. The estimated parameter values suggested that the time compression resulted from an expectation that the actions would immediately cause sensory outcomes. Furthermore, I investigated the algorithm that realized this BCI and found probability-matching to be a plausible candidate; people might heuristically reconstruct event timing depending on causal uncertainty rather than optimally integrating causal and temporal posteriors. The evidence demonstrated the utility of computational modeling to investigate how humans infer the causal and temporal structures of events and individual differences in that process.

Frontal Norepinephrine Represents a Threat Prediction Error Under Uncertainty

BackgroundTo adapt to threats in the environment, animals must predict them and engage in defensive behavior. While the representation of a prediction error signal for reward has been linked to dopamine, a neuromodulatory prediction error for aversive learning has not been identified. MethodsWe measured and manipulated norepinephrine release during threat learning using optogenetics and a novel fluorescent norepinephrine sensor. ResultsWe found that norepinephrine response to conditioned stimuli reflects aversive memory strength. When delays between auditory stimuli and footshock are introduced, norepinephrine acts as a prediction error signal. However, temporal difference prediction errors do not fully explain norepinephrine dynamics. To explain noradrenergic signaling, we used an updated reinforcement learning model with uncertainty about time and found that it explained norepinephrine dynamics across learning and variations in temporal and auditory task structure. ConclusionsNorepinephrine thus combines cognitive and affective information into a predictive signal and links time with the anticipation of danger.

TSAGNN: Temporal link predict method based on two stream adaptive graph neural network

Temporal link prediction based on graph neural networks has become a hot spot in the field of complex networks. To solve the problems of the existing temporal link prediction methods based on graph neural networks do not consider the future time-domain features and spatial-domain features are limited used, this paper proposes a novel temporal link prediction method based on two streams adaptive graph neural networks. Firstly, the network topology features are extracted from the micro, meso, and middle perspectives. Combined with the adaptive mechanism of convolution and self-attention, the preprocessing of the feature extraction is more effective; Secondly, an extended bi-directional long short-term memory network is proposed, which uses graph convolution to process topological features, and recursively learns the state vectors of the target snapshot by using the future time-domain information and the past historical information; Thirdly, the location coding is replaced by the time-coding for the transformer mechanism, so that past information and future information can be learned from each other, and the time-domain information of the network can be further mined; Finally, a novel two-stream network framework is proposed, which combines the processing results of point features and edge features. The experimental results on 9 data sets show that the proposed method has a better prediction effect and better robustness than the classical graph neural network methods.

A novel method for predicting fluid–structure interaction with large deformation based on masked deep neural network

Traditional fluid–structure interaction (FSI) simulation is computationally demanding, especially for bi-directional FSI problems. To address this, a masked deep neural network (MDNN) is developed to quickly and accurately predict the unsteady flow field. By integrating the MDNN with a structural dynamic solver, an FSI system is proposed to perform simulation of a flexible vertical plate oscillation in fluid with large deformation. The results show that both the flow field prediction and structure response are consistent with the traditional FSI system. Furthermore, the masked method is highly effective in mitigating error accumulation during temporal flow field predictions, making it applicable to various deformation problems. Notably, the proposed model reduces the computational time to a millisecond scale for each step regarding the fluid part, resulting in an increase in nearly two orders of magnitude in computational speed, which greatly enhances the computational speed of the FSI system.

ConTIG: Continuous representation learning on temporal interaction graphs

Representation learning on temporal interaction graphs (TIG) aims to model complex networks with the dynamic evolution of interactions on a wide range of web and social graph applications. However, most existing works on TIG either (a) rely on discretely updated node embeddings merely when an interaction occurs that fail to capture the continuous evolution of embedding trajectories of nodes, or (b) overlook the rich temporal patterns hidden in the ever-changing graph data that presumably lead to sub-optimal models. In this paper, we propose a two-module framework named ConTIG, a novel representation learning method on TIG that captures the continuous dynamic evolution of node embedding trajectories. With two essential modules, our model exploits three-fold factors in dynamic networks including latest interaction, neighbor features, and inherent characteristics. In the first update module, we employ a continuous inference block to learn the nodes’ state trajectories from time-adjacent interaction patterns using ordinary differential equations. In the second transform module, we introduce a self-attention mechanism to predict future node embeddings by aggregating historical temporal interaction information. Experiment results demonstrate the superiority of ConTIG on temporal link prediction, temporal node recommendation, and dynamic node classification tasks of four datasets compared with a range of state-of-the-art baselines, especially for long-interval interaction prediction.

Brain-Inspired Reservoir Computing Using Memristors with Tunable Dynamics and Short-Term Plasticity.

Recent advancements in reservoir computing (RC) research have created a demand for analogue devices with dynamics that can facilitate the physical implementation of reservoirs, promising faster information processing while consuming less energy and occupying a smaller area footprint. Studies have demonstrated that dynamic memristors, with nonlinear and short-term memory dynamics, are excellent candidates as information-processing devices or reservoirs for temporal classification and prediction tasks. Previous implementations relied on nominally identical memristors that applied the same nonlinear transformation to the input data, which is not enough to achieve a rich state space. To address this limitation, researchers either diversified the data encoding across multiple memristors or harnessed the stochastic device-to-device variability among the memristors. However, this approach requires additional preprocessing steps and leads to synchronization issues. Instead, it is preferable to encode the data once and pass them through a reservoir layer consisting of memristors with distinct dynamics. Here, we demonstrate that ion-channel-based memristors with voltage-dependent dynamics can be controllably and predictively tuned through the voltage or adjustment of the ion channel concentration to exhibit diverse dynamic properties. We show, through experiments and simulations, that reservoir layers constructed with a small number of distinct memristors exhibit significantly higher predictive and classification accuracies with a single data encoding. We found that for a second-order nonlinear dynamical system prediction task, the varied memristor reservoir experimentally achieved an impressive normalized mean square error of 1.5 × 10-3, using only five distinct memristors. Moreover, in a neural activity classification task, a reservoir of just three distinct memristors experimentally attained an accuracy of 96.5%. This work lays the foundation for next-generation physical RC systems that can exploit the complex dynamics of their diverse building blocks to achieve increased signal processing capabilities.

Dynamic Graph Convolutional Network-Based Prediction of the Urban Grid-Level Taxi Demand–Supply Imbalance Using GPS Trajectories

The objective imbalance between the taxi supply and demand exists in various areas of the city. Accurately predicting this imbalance helps taxi companies with dispatching, thereby increasing their profits and meeting the travel needs of residents. The application of Graph Convolutional Networks (GCNs) in traffic forecasting has inspired the development of a spatial–temporal model for grid-level prediction of the taxi demand–supply imbalance. However, spatial–temporal GCN prediction models conventionally capture only static inter-grid correlation features. This research aims to address the dynamic influences caused by taxi mobility and the variations of other transportation modes on the demand–supply dynamics between grids. To achieve this, we employ taxi trajectory data and develop a model that incorporates dynamic GCN and Gated Recurrent Units (GRUs) to predict grid-level imbalances. This model captures the dynamic inter-grid influences between neighboring grids in the spatial dimension. It also identifies trends and periodic changes in the temporal dimension. The validation of this model, using taxi trajectory data from Shenzhen city, indicates superior performance compared to classical time-series models and spatial–temporal GCN models. An ablation study is conducted to analyze the impact of various factors on the predictive accuracy. This study demonstrates the precision and applicability of the proposed model.

Feeding predictability as a cognitive enrichment protects brain function and physiological status in rainbow trout: a multidisciplinary approach to assess fish welfare

Cognitive enrichment is a promising but understudied type of environmental enrichment that aims to stimulate the cognitive abilities of animals by providing them with more opportunities to interact with (namely, to predict events than can occur) and to control their environment. In a previous study, we highlighted that farmed rainbow trout can predict daily feedings after two weeks of conditioning, the highest conditioned response being elicited by the combination of both temporal and signalled predictability. In the present study, we tested the feeding predictability that elicited the highest conditioned response in rainbow trout (both temporal and signalled by bubbles, BUBBLE + TIME treatment) as a cognitive enrichment strategy to improve their welfare. We thus analysed the long-term effects of this feeding predictability condition as compared with an unpredictable feeding condition (RANDOM treatment) on the welfare of rainbow trout, including the markers in the modulation of brain function, through a multidisciplinary approach. To reveal the brain regulatory pathways and networks involved in the long-term effects of feeding predictability, we measured gene markers of cerebral activity and plasticity, neurotransmitter pathways and physiological status of fish (oxidative stress, inflammatory status, cell type and stress status). After almost three months under these predictability conditions of feeding, we found clear evidence of improved welfare in fish from BUBBLE + TIME treatment. Feeding predictability allowed for a food anticipatory activity and resulted in fewer aggressive behaviours, burst of accelerations, and jumps before mealtime. BUBBLE + TIME fish were also less active between meals, which is in line with the observed decreased expression of transcripts related to the dopaminergic system. BUBBLE + TIME fish tented to present fewer eroded dorsal fin and infections to the pathogen Flavobacterium psychrophilum. Decreased expression of most of the studied mRNA involved in oxidative stress and immune responses confirm these tendencies else suggesting a strong role of feeding predictability on fish health status and that RANDOM fish may have undergone chronic stress. Fish emotional reactivity while isolated in a novel-tank as measured by fear behaviour and plasma cortisol levels were similar between the two treatments, as well as fish weight and size. To conclude, signalled combined with temporal predictability of feeding appears to be a promising approach of cognitive enrichment to protect brain function via the physiological status of farmed rainbow trout in the long term.

What is a Rhythm for the Brain? The Impact of Contextual Temporal Variability on Auditory Perception.

Temporal predictions can be formed and impact perception when sensory timing is fully predictable: for instance, the discrimination of a target sound is enhanced if it is presented on the beat of an isochronous rhythm. However, natural sensory stimuli, like speech or music, are not entirely predictable, but still possess statistical temporal regularities. We investigated whether temporal expectations can be formed in non-fully predictable contexts, and how the temporal variability of sensory contexts affects auditory perception. Specifically, we asked how "rhythmic" an auditory stimulation needs to be in order to observe temporal predictions effects on auditory discrimination performances. In this behavioral auditory oddball experiment, participants listened to auditory sound sequences where the temporal interval between each sound was drawn from gaussian distributions with distinct standard deviations. Participants were asked to discriminate sounds with a deviant pitch in the sequences. Auditory discrimination performances, as measured with deviant sound discrimination accuracy and response times, progressively declined as the temporal variability of the sound sequence increased. Moreover, both global and local temporal statistics impacted auditory perception, suggesting that temporal statistics are promptly integrated to optimize perception. Altogether, these results suggests that temporal predictions can be set up quickly based on the temporal statistics of past sensory events and are robust to a certain amount of temporal variability. Therefore, temporal predictions can be built on sensory stimulations that are not purely periodic nor temporally deterministic.

Site selection and capacity determination of charging stations considering the uncertainty of users’ dynamic charging demands

Aiming at the problems of high investment and low efficiency in the planning and construction of electric vehicle (EV) charging stations in cities, an optimization model for site selection and capacity determination of charging stations considering the uncertainty of users’ dynamic charging demands is proposed. Firstly, based on the travel chain theory and the Origin-Destination (OD) matrix, the travel characteristics of EVs are studied, and the spatial and temporal distribution prediction model of EV charging load is established through the dynamic Dijkstra algorithm combined with the Monte Carlo method. Secondly, a site selection model for the charging station is established which takes the minimum annualized cost of the charging station operator and the annualized economic loss of the EV users as the goal. At the same time, the weighted Voronoi diagram and Adaptive Simulated Annealing Particle Swarm Optimization algorithm (ASPSO) are adopted to determine the optimal number/site selection and service scope of charging stations. Finally, an uncertain scenario set is introduced into the capacity determination model to describe the uncertainty of the users’ dynamic charging demands, and the robust optimization theory is utilized to solve the capacity of the charging station. A case study is carried out for the EV charging station planning problem in some urban areas of a northern city, and the validity of the model is verified.

Speedup and efficiency of computational parallelization: A unifying approach and asymptotic analysis

In high performance computing environments, we observe an ongoing increase in the available number of cores. For example, the current TOP500 list reveals that nine clusters have more than 1 million cores. This development calls for re-emphasizing performance (scalability) analysis and speedup laws as suggested in the literature (e.g., Amdahl's law and Gustafson's law), with a focus on asymptotic performance. Understanding speedup and efficiency issues of algorithmic parallelism is useful for several purposes, including the optimization of system operations, temporal predictions on the execution of a program, the analysis of asymptotic properties, and the determination of speedup bounds. However, the literature is fragmented and shows a large diversity and heterogeneity of speedup models and laws. These phenomena make it challenging to obtain an overview of the models and their relationships, to identify the determinants of performance in a given algorithmic and computational context, and, finally, to determine the applicability of performance models and laws to a particular parallel computing setting. In this work, I provide a generic speedup (and thus also efficiency) model for homogeneous computing environments. My approach generalizes many prominent models suggested in the literature and allows showing that they can be considered special cases of a unifying approach. The genericity of the unifying speedup model is achieved through parameterization. Considering combinations of parameter ranges, I identify six different asymptotic speedup cases and eight different asymptotic efficiency cases. Jointly applying these speedup and efficiency cases, I derive eleven scalability cases, from which I build a scalability typology. Researchers can draw upon my suggested typology to classify their speedup model and to determine the asymptotic behavior when the number of parallel processing units increases. Also, the description of two computational experiments demonstrates the practical application of the model and the typology. In addition, my results may be used and extended in future research to address various extensions of my setting.

The MS-RadarFormer: A Transformer-Based Multi-Scale Deep Learning Model for Radar Echo Extrapolation

As a spatial–temporal sequence prediction task, radar echo extrapolation aims to predict radar echoes’ future movement and intensity changes based on historical radar observations. Two urgent issues still need to be addressed in deep learning radar echo extrapolation models. First, the predicted radar echo sequences often exhibit echo-blurring phenomena. Second, over time, the output echo intensities from the model gradually weaken. In this paper, we propose a novel model called the MS-RadarFormer, a Transformer-based multi-scale deep learning model for radar echo extrapolation, to mitigate the two above issues. We introduce a multi-scale design in the encoder–decoder structure and a Spatial–Temporal Attention block to improve the precision of radar echoes and establish long-term dependencies of radar echo features. The model uses a non-autoregressive approach for echo prediction, avoiding accumulation errors during the recursive generation of future echoes. Compared to the baseline, our model shows an average improvement of 15.8% in the critical success index (CSI), an average decrease of 8.3% in the false alarm rate (FAR), and an average improvement of 16.2% in the Heidke skill score (HSS).